Search Results for author: Nassim Mokhtari

Found 3 papers, 3 papers with code

Enhanced Spatio- Temporal Image Encoding for Online Human Activity Recognition

1 code implementation • International Conference on Machine Learning and Applications (ICMLA) 2023 • Nassim Mokhtari, Vincent Fer, Alexis Nédélec, Marlene Gilles, Pierre De Loor

It can be done using 3D skeleton data extracted from a RGB+D camera.

Ranked #1 on Human Activity Recognition on OAD dataset

Human Activity Recognition Time Series +1

Paper
Code

Improving Neural Architecture Search by Mixing a FireFly algorithm with a Training Free Evaluation

1 code implementation • International Joint Conference on Neural Networks (IJCNN) 2022 • Nassim Mokhtari, Alexis Nédélec, Marlène Gilles, Pierre De Loor

Neural Architecture Search (NAS) algorithms are used to automate the design of deep neural networks.

Ranked #1 on Neural Architecture Search on NAS-Bench-201

Neural Architecture Search valid

Paper
Code

Human Activity Recognition: A Spatio-temporal Image Encoding of 3D Skeleton Data for Online Action Detection

1 code implementation • International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications VISIGRAPP 2020 • Nassim Mokhtari, Alexis Nédélec, Pierre De Loor

Human activity recognition (HAR) based on skeleton data that can be extracted from videos (Kinect for example) , or provided by a depth camera is a time series classification problem, where handling both spatial and temporal dependencies is a crucial task, in order to achieve a good recognition.

Ranked #3 on Human Activity Recognition on OAD dataset

Human Activity Recognition Online Action Detection +2

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.